© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 54567
    Prev
    Next
    INDEX
    Explanations

    Changes and progress

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    “.
    -0.07
     vl
    -0.06
     pop
    -0.06
     갈
    -0.06
     digits
    -0.06
     biến
    -0.06
     ends
    -0.06
    IAL
    -0.06
     Eastern
    -0.06
     tableName
    -0.06
    POSITIVE LOGITS
    Proposal
    0.07
    _repeat
    0.07
    uuml
    0.07
    goo
    0.07
     trọng
    0.07
     değerlendir
    0.07
    :<?
    0.06
     EXCEPTION
    0.06
     ilgi
    0.06
    (aa
    0.06
    Activations Density 0.001%

    No Known Activations